AI/ML Engineer

Triunity Software•Oakland, CA

About The Position

Triunity Software is seeking a talented and passionate AI/ML Engineer to join its team in New Jersey. The role involves developing cutting-edge artificial intelligence and machine learning solutions that turn complex data into intelligent systems with real-world impact. The engineer will build and support cloud-based services and production AI/LLM applications, with a focus on generative AI, retrieval-augmented generation, evaluation, observability, and enterprise requirements. The position is part of a fast-paced, innovative environment working on client projects and complex technology solutions.

Requirements

At least 5 years of overall software engineering experience.
At least 2 years of hands-on LLM/generative AI development experience.
Strong proficiency in Python 3.11 or later, including asynchronous programming, type annotations, and automated testing.
Hands-on experience with LLM/generative AI application development.
Strong experience with RAG, embedding models, indexing strategies, and retrieval optimization.
Experience with at least one LLM orchestration framework: LangGraph, LangChain, LlamaIndex, Semantic Kernel, AutoGen, or Amazon Bedrock Agents.
Expertise in LLM evaluation methodologies, golden datasets, evaluation metrics, and LLM-as-a-judge techniques.
Experience developing cloud-based services, REST APIs, data pipelines, and event-driven workers.
Knowledge of AI observability, tracing, structured logging, quality monitoring, and cost optimization.
Exposure to enterprise security and compliance reviews.

Nice To Haves

Experience with FastAPI, Pydantic, PostgreSQL, Aurora PostgreSQL, and vector extensions.
Experience with AgentCore and Agentic AI.
Experience with Kubernetes, Helm, Terraform, and CI/CD.
Experience with Apache Kafka and event-driven architecture.
Experience with Datadog and OpenTelemetry.
Experience with Document AI, OCR, intelligent document processing, and human-in-the-loop workflows.
Experience in financial services, insurance, healthcare, or other regulated industries.

Responsibilities

Develop LLM and generative AI applications, including retrieval-augmented generation solutions.
Build cloud-based services, REST APIs, data pipelines, and event-driven workers.
Deploy enterprise-grade AI/LLM applications into production.
Own and support live AI applications, including incident management, root-cause analysis, regression management, and production enhancements.
Apply LLM evaluation methodologies, golden datasets, evaluation metrics, and LLM-as-a-judge techniques.
Monitor AI applications using tracing, structured logging, quality monitoring, and cost optimization practices.
Work within enterprise security, compliance, and governance requirements.